6 papers
RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning
Chuanpu Liu, Miao Yu, Yikai Cai +5
Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. However, existing circuit studie…
In-Place Instruction Following in Diffusion Language Models
Zheng Nie, Zherui Li, Jiaming Zhang +3
Diffusion Large Language Models (dLLMs) generate text via bidirectional iterative denoising, naturally supporting user-specified constraints anchored at arbitrary output positions,…
SafeSeek: Universal Attribution of Safety Circuits in Language Models
Miao Yu, Siyuan Fu, Moayad Aloqaily +6
Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional co…
MAS: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
Kun Wang, Guibin Zhang, ManKit Ye +6
The past two years have witnessed the meteoric rise of Large Language Model (LLM)-powered multi-agent systems (MAS), which harness collective intelligence and exhibit a remarkable…
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
Zherui Li, Zheng Nie, Zhenhong Zhou +7
The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from Autoregressive LLMs, stemming from th…
Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation
Yuanhe Zhang, Fangzhou Xie, Zhenhong Zhou +4
Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise an…